INDEX

Explanations

references to patent and approval numbers or related legal documentation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

żli

-0.59

oa̍t

-0.57

 kteří

-0.52

 Piers

-0.52

 ktorí

-0.51

etheless

-0.51

".

-0.51

FetchType

-0.50

elv

-0.49

POSITIVE LOGITS

 number

0.76

number

0.75

 Number

0.74

№

0.71

withIdentifier

0.71

№

0.69

Номер

0.69

 číslo

0.68

 NUMBER

0.68

 numbers

0.66

Activations Density 0.438%

references to patent and approval numbers or related legal documentation

No Comments

No Known Activations